{"id":13983553,"url":"https://github.com/station-10/awesome-marketing-machine-learning","last_synced_at":"2025-07-21T23:31:00.026Z","repository":{"id":187822508,"uuid":"676990791","full_name":"station-10/awesome-marketing-machine-learning","owner":"station-10","description":"A curated list of awesome machine learning libraries for marketing, including media mix models, multi touch attribution, causal inference and more","archived":false,"fork":false,"pushed_at":"2024-05-01T11:06:06.000Z","size":65,"stargazers_count":88,"open_issues_count":0,"forks_count":9,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-11-14T04:02:31.535Z","etag":null,"topics":["attribution","awesome-list","causal-inference","clv","machine-learning","marketing","media","mmm","mta","recommendation-system","synthetic-control","time-series-forecasting"],"latest_commit_sha":null,"homepage":"http://www.station10.co.uk","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/station-10.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-08-10T13:35:17.000Z","updated_at":"2024-11-11T13:35:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"656b3f48-b549-463c-aabc-bab4839ce7f3","html_url":"https://github.com/station-10/awesome-marketing-machine-learning","commit_stats":null,"previous_names":["station-10/awesome-marketing-machine-learning"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/station-10%2Fawesome-marketing-machine-learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/station-10%2Fawesome-marketing-machine-learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/station-10%2Fawesome-marketing-machine-learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/station-10%2Fawesome-marketing-machine-learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/station-10","download_url":"https://codeload.github.com/station-10/awesome-marketing-machine-learning/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226998689,"owners_count":17715368,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["attribution","awesome-list","causal-inference","clv","machine-learning","marketing","media","mmm","mta","recommendation-system","synthetic-control","time-series-forecasting"],"created_at":"2024-08-09T05:01:48.447Z","updated_at":"2024-11-28T22:30:33.149Z","avatar_url":"https://github.com/station-10.png","language":null,"funding_links":[],"categories":["Programming Language Lists","Related Lists","🚀 GitHub Repositories"],"sub_categories":["Python Lists","🌟 **Real-World Magic**"],"readme":"[![Awesome](images/awesome.svg)](https://github.com/sindresorhus/awesome)\n[![Maintenance](https://img.shields.io/badge/Maintained%3F-YES-green.svg)](https://github.com/EthicalML/awesome-production-machine-learning/graphs/commit-activity)\n![GitHub](https://img.shields.io/badge/Languages-MULTI-blue.svg)\n![GitHub](https://img.shields.io/badge/License-MIT-lightgrey.svg)\n[![GitHub](https://img.shields.io/badge/Twitter-1DA1F2?style=for-the-badge\u0026logo=twitter\u0026logoColor=white)](https://twitter.com/station10_uk)\n[![GitHub](https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge\u0026logo=linkedin\u0026logoColor=white)](https://www.linkedin.com/company/-station10-)\n\n# awesome-marketing-machine-learning\n\nA curated list of awesome machine learning libraries for marketing. Inspired by both\n[awesome-production-machine-learning](https://github.com/EthicalML/awesome-production-machine-learning) and\n[awesome-machine-learning](https://github.com/josephmisiti/awesome-machine-learning),\nand created and maintained by [Station 10](https://station10.co.uk/).\n\nNote that some packages could fit into more than one section. This has been noted in the descriptions so be sure to Ctrl + F as well as exploring by\nsections.\n\nWant to contribute? Please raise a Pull Request or an issue. If you find this useful please drop a ⭐️. This helps motivate us and others to update and\nmaintain the list.\n\nAll packages are Python based unless otherwise stated. We welcome contributions from R Users!\n\n# Main Content\n\n## Attribution\n\n* [ChannelAttribution](https://github.com/DavideAltomare/ChannelAttribution/tree/master) ![Github Stars](https://img.shields.io/github/stars/DavideAltomare/ChannelAttribution.svg?style=social)\nPython and R library that employs a k-order Markov representation to identify structural correlations in customer journey data.\n* [fractribution](https://github.com/google/fractribution) ![Github Stars](https://img.shields.io/github/stars/google/fractribution.svg?style=social)\n Data driven MTA by Google.\n* [Marketing-Attribution-Models](https://github.com/DP6/Marketing-Attribution-Models) ![Github Stars](https://img.shields.io/github/stars/DP6/Marketing-Attribution-Models.svg?style=social)\n Heuristic and data driven Multi Touch Attribution.\n* [markov-chain-attribution](https://github.com/jerednel/markov-chain-attribution) ![Github Stars](https://img.shields.io/github/stars/jerednel/markov-chain-attribution.svg?style=social)\n Leverages a first order Markov chain to reallocate conversions.\n* [mta](https://github.com/eeghor/mta) ![Github Stars](https://img.shields.io/github/stars/eeghor/mta.svg?style=social)\n Various data driven Multi Touch Attribution algorithms.\n* [pychattr](https://github.com/jmwoloso/pychattr) ![Github Stars](https://img.shields.io/github/stars/jmwoloso/pychattr.svg?style=social)\n Python implementation of the excellent R ChannelAttribution library.\n* [shapley](https://github.com/hartmann-lars/shapley) ![Github Stars](https://img.shields.io/github/stars/hartmann-lars/shapley.svg?style=social)\n Shapley Values For Attribution Modelling.\n* [shapley-attribution-model-zhao-naive](https://github.com/ianchute/shapley-attribution-model-zhao-naive) ![Github Stars](https://img.shields.io/github/stars/ianchute/shapley-attribution-model-zhao-naive.svg?style=social)\n Shapley Value Methods for Attribution Modeling (Naive, Set-based).\n\n## Causal Inference\n\n* [CausalImpact](https://github.com/google/CausalImpact) ![Github Stars](https://img.shields.io/github/stars/google/CausalImpact.svg?style=social)\n(R)  Causal Inference using Bayesian structural time-series models by Google.\n* [causalml](https://github.com/uber/causalml) ![Github Stars](https://img.shields.io/github/stars/uber/causalml.svg?style=social)\n Uplift modeling and causal inference with ML by Uber.\n* [CausalPy](https://github.com/pymc-labs/CausalPy) ![Github Stars](https://img.shields.io/github/stars/pymc-labs/CausalPy.svg?style=social)\n Causal Inference \u0026 Synthetic Control. Supports fitting with `scikit-learn` and `PyMC` models.\n* [dowhy](https://github.com/py-why/dowhy) ![Github Stars](https://img.shields.io/github/stars/py-why/dowhy.svg?style=social)\n Causal Inference that supports explicit modeling and testing of causal assumptions.\n* [SyntheticControlMethods](https://github.com/OscarEngelbrektson/SyntheticControlMethods) ![Github Stars](https://img.shields.io/github/stars/OscarEngelbrektson/SyntheticControlMethods.svg?style=social)\n Causal inference using Synthetic Control.\n* [tfcausalimpact](https://github.com/WillianFuks/tfcausalimpact) ![Github Stars](https://img.shields.io/github/stars/WillianFuks/tfcausalimpact.svg?style=social)\n Google's [CausalImpact](https://github.com/google/CausalImpact) Algorithm implemented on top of [TensorFlow Probability](https://github.com/tensorflow/probability).\n* [upliftml](https://github.com/bookingcom/upliftml) ![Github Stars](https://img.shields.io/github/stars/bookingcom/upliftml.svg?style=social)\nScalable unconstrained and constrained uplift modeling from experimental data using PySpark and H20.\n* [scikit-uplift](https://github.com/maks-sh/scikit-uplift) ![Github Stars](https://img.shields.io/github/stars/maks-sh/scikit-uplift.svg?style=social)\n* Uplift modeling python package that provides fast sklearn-style models implementation, evaluation metrics and visualization tools.\n\n## Churn / CLV\n\n* [btyd](https://github.com/ColtAllen/btyd) ![Github Stars](https://img.shields.io/github/stars/ColtAllen/btyd.svg?style=social)\n Buy Till You Die and CLV statistical models in Python.\n* [lifetimes](https://github.com/CamDavidsonPilon/lifetimes) ![Github Stars](https://img.shields.io/github/stars/CamDavidsonPilon/lifetimes.svg?style=social)\n CLV and Churn modelling. Deprecated and incorporated into [pymc-marketing](https://github.com/pymc-labs/pymc-marketing).\n* [lucius-ltv](https://github.com/plexagon/lucius-ltv) ![Github Stars](https://img.shields.io/github/stars/plexagon/lucius-ltv.svg?style=social)\n CLV for subscriptions.\n\n## Data\n* [gapandas4](https://github.com/practical-data-science/gapandas4) ![Github Stars](https://img.shields.io/github/stars/practical-data-science/gapandas4.svg?style=social)\nPython package for querying the Google Analytics Data API for GA4 and displaying the results in a Pandas dataframe.\n\n## Econometrics\n\n* [EconML](https://github.com/py-why/EconML) ![Github Stars](https://img.shields.io/github/stars/py-why/EconML.svg?style=social)\n AI, Econometrics and Causal Inference modelling.\n* [statsmodels](https://github.com/statsmodels/statsmodels) ![Github Stars](https://img.shields.io/github/stars/statsmodels/statsmodels.svg?style=social)\n Statistical modeling including time series and econometrics.\n\n## Geo Experimentation\n\n* [trimmed_match](https://github.com/google/trimmed_match) ![Github Stars](https://img.shields.io/github/stars/google/trimmed_match.svg?style=social)\n Ad effectiveness through the design and analysis of randomized Geo Experiments by Google.\n* [matched_markets](https://github.com/google/matched_markets) ![Github Stars](https://img.shields.io/github/stars/google/matched_markets.svg?style=social)\n Time-Based regression matched markets approach for designing Geo Experiments by Google.\n* [GeoexperimentsResearch](https://github.com/google/GeoexperimentsResearch) ![Github Stars](https://img.shields.io/github/stars/facebookincubator/GeoLift.svg?style=social)\n(R) Open-source implementation of the geo experiment analysis methodology developed at Google (Archived)\n* [GeoLift](https://github.com/facebookincubator/GeoLift) ![Github Stars](https://img.shields.io/github/stars/facebookincubator/GeoLift.svg?style=social)\n Geo Experimentation methodology based on Synthetic Control Methods used to measure lift of ad campaigns by Facebook.\n\n## Media / Marketing Mix Models\n\n* [BayesianMMM](https://github.com/leopoldavezac/BayesianMMM) ![Github Stars](https://img.shields.io/github/stars/leopoldavezac/BayesianMMM.svg?style=social)\n Bayesian Media Mix mMdelling with shape and carryover effect.\n* [dammmdatagen](https://github.com/DoktorMike/dammmdatagen) ![Github Stars](https://img.shields.io/github/stars/DoktorMike/dammmdatagen.svg?style=social)\n (R) Media Mix Modeling Data Generator.\n* [lightweight-mmm](https://github.com/google/lightweight_mmm) ![Github Stars](https://img.shields.io/github/stars/google/lightweight_mmm.svg?style=social)\n Bayesian Media Mix Models by Google.\n* [mamimo](https://github.com/Garve/mamimo) ![Github Stars](https://img.shields.io/github/stars/Garve/mamimo.svg?style=social)\n Small Media Mix Models designed to be used in conjunction with ML libraries (e.g. SKL)\n* [mmm-stan](https://github.com/sibylhe/mmm_stan) ![Github Stars](https://img.shields.io/github/stars/sibylhe/mmm_stan.svg?style=social)\n Multiplicative Media Media Mix Model.\n* [pymc-marketing](https://github.com/pymc-labs/pymc-marketing) ![Github Stars](https://img.shields.io/github/stars/pymc-labs/pymc-marketing.svg?style=social)\n Bayesian Media Mix, Adstock, Saturation Customer Lifetime Value \u0026 Churn models.\n* [Robyn](https://github.com/facebookexperimental/Robyn) ![Github Stars](https://img.shields.io/github/stars/facebookexperimental/Robyn.svg?style=social)\n (R) Bayesian Media Mix Models by Facebook.\n\n## Personalisation / Segmentation\n\n* [amazon-denseclus](https://github.com/awslabs/amazon-denseclus) ![Github Stars](https://img.shields.io/github/stars/awslabs/amazon-denseclus.svg?style=social)\nPython module for clustering both categorical and numerical data using UMAP and HDBSCAN by Amazon.\n* [rfm](https://github.com/sonwanesuresh95/rfm) ![Github Stars](https://img.shields.io/github/stars/sonwanesuresh95/rfm.svg?style=social)\n RFM Analysis and Customer Segmentation.\n* [retentioneering-tools](https://github.com/retentioneering/retentioneering-tools) ![Github Stars](https://img.shields.io/github/stars/retentioneering/retentioneering-tools.svg?style=social)\n Retentioneering: product analytics, data-driven customer journey map optimization, marketing analytics, web analytics, transaction analytics, graph visualization, and behavioral segmentation\n* [ecommercetools](https://github.com/practical-data-science/ecommercetools) ![Github Stars](https://img.shields.io/github/stars/practical-data-science/ecommercetools.svg?style=social)\nData science toolkit for those working in technical ecommerce, marketing science, and technical seo and includes a wide range of features to aid analysis and model building. \n\n## Recommendation Systems\n\n* [lightfm](https://github.com/lyst/lightfm) ![Github Stars](https://img.shields.io/github/stars/lyst/lightfm.svg?style=social)\n Implementation of LightFM, a hybrid recommendation algorithm.\n* [openrec](https://github.com/ylongqi/openrec) ![Github Stars](https://img.shields.io/github/stars/ylongqi/openrec.svg?style=social) \n Open-source and modular library for neural network-inspired recommendation algorithms.\n* [recmetrics](https://github.com/statisticianinstilettos/recmetrics) ![Github Stars](https://img.shields.io/github/stars/statisticianinstilettos/recmetrics.svg?style=social)\n A library of metrics for evaluating recommender systems\n* [recommenders](https://github.com/microsoft/recommenders) ![Github Stars](https://img.shields.io/github/stars/microsoft/recommenders.svg?style=social) \n Best Practices on Recommendation Systems by Microsoft.\n* [Surprise](https://github.com/NicolasHug/Surprise) ![Github Stars](https://img.shields.io/github/stars/NicolasHug/Surprise.svg?style=social)\n Scikit for building and analyzing recommender systems that deal with explicit rating data.\n\n## Time Series\n\n* [darts](https://github.com/unit8co/darts) ![Github Stars](https://img.shields.io/github/stars/unit8co/darts.svg?style=social)\nPython library for user-friendly forecasting and anomaly detection on time series built using SKL conventions.\n* [gluonts](https://github.com/awslabs/gluonts) ![Github Stars](https://img.shields.io/github/stars/awslabs/gluonts.svg?style=social)\nProbabilistic time series modeling, focusing on deep learning based models, based on PyTorch and MXNet.\n* [neural_prophet](https://github.com/ourownstory/neural_prophet) ![Github Stars](https://img.shields.io/github/stars/ourownstory/neural_prophet.svg?style=social)\nFramework for interpretable time series forecasting built on PyTorch.\n* [orbit](https://github.com/uber/orbit) ![Github Stars](https://img.shields.io/github/stars/uber/orbit.svg?style=social)\nPython package for Bayesian time series forecasting and inference by Uber.\n* [pmdarima](https://github.com/alkaline-ml/pmdarima) ![Github Stars](https://img.shields.io/github/stars/alkaline-ml/pmdarima.svg?style=social)\n* Pmdarima is a statistical library designed to fill the void in Python's time series analysis capabilities.\n* [prophet](https://github.com/facebook/prophet) ![Github Stars](https://img.shields.io/github/stars/facebook/prophet.svg?style=social)\nAdditive time series modelling by Facebook.\n* [sktime](https://github.com/sktime/sktime) ![Github Stars](https://img.shields.io/github/stars/sktime/sktime.svg?style=social)\nA unified framework for ML with Time Eeries.\n* [statsforecast](https://github.com/Nixtla/statsforecast) ![Github Stars](https://img.shields.io/github/stars/Nixtla/statsforecast.svg?style=social)\n Lightning ⚡️ fast forecasting with statistical and econometric models.\n* [stumpy](https://github.com/TDAmeritrade/stumpy) ![Github Stars](https://img.shields.io/github/stars/TDAmeritrade/stumpy.svg?style=social)\nSTUMPY  computes something called the matrix profile, which is just an academic way of saying \"for every subsequence automatically identify its corresponding nearest-neighbor\"\n* [temporian](https://github.com/google/temporian) ![Github Stars](https://img.shields.io/github/stars/google/temporian.svg?style=social)\n Temporian is an open-source Python library for preprocessing ⚡ and feature engineering 🛠 temporal data 📈 for machine learning applications 🤖.\n* [tbats](https://github.com/intive-DataScience/tbats) ![Github Stars](https://img.shields.io/github/stars/intive-DataScience/tbats.svg?style=social)\nBATS and TBATS time series forecasting\n* [tsfresh](https://github.com/blue-yonder/tsfresh) ![Github Stars](https://img.shields.io/github/stars/blue-yonder/tsfresh.svg?style=social)\nTime Series Feature extraction based on scalable hypothesis tests.\n* [tslearn](https://github.com/tslearn-team/tslearn) ![Github Stars](https://img.shields.io/github/stars/tslearn-team/tslearn.svg?style=social)\nThe machine learning toolkit for time series analysis in Python.\n\n## Survival Analysis\n\n* [lifelines](https://github.com/CamDavidsonPilon/lifelines) ![Github Stars](https://img.shields.io/github/stars/CamDavidsonPilon/lifelines.svg?style=social)\n lifelines is a pure Python implementation of the best parts of survival analysis.\n* [pysurvival](https://github.com/square/pysurvival) ![Github Stars](https://img.shields.io/github/stars/square/pysurvival.svg?style=social)\n An open source python package for Survival Analysis modeling.\n* [scikit-survival](https://github.com/sebp/scikit-survival) ![Github Stars](https://img.shields.io/github/stars/sebp/scikit-survival.svg?style=social)\n Survival analysis built on top of scikit-learn.\n\n## Synthetic Control\n\n* [pysyncon](https://github.com/sdfordham/pysyncon) ![Github Stars](https://img.shields.io/github/stars/sdfordham/pysyncon.svg?style=social)\n Multiple Synthetic Control implementations.\n* [scpi](https://github.com/nppackages/scpi) ![Github Stars](https://img.shields.io/github/stars/nppackages/scpi.svg?style=social)\n Provides Python, R and Stata implementations of estimation and inference procedures for synthetic control methods.\n* [SparseSC](https://github.com/microsoft/SparseSC) ![Github Stars](https://img.shields.io/github/stars/microsoft/SparseSC.svg?style=social)\n Sparse Synthetic Control Models in Python by Microsoft.\n\n## Synthetic Data\n\n* [Decoy](https://github.com/EqualExperts/decoy) ![Github Stars](https://img.shields.io/github/stars/EqualExperts/decoy.svg?style=social)\nSynthetic Data Generator using DuckDB at its core.\n* [SDV](https://github.com/sdv-dev/SDV) ![Github Stars](https://img.shields.io/github/stars/sdv-dev/SDV.svg?style=social)\nPython library designed to be your one-stop shop for creating tabular synthetic data.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstation-10%2Fawesome-marketing-machine-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fstation-10%2Fawesome-marketing-machine-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstation-10%2Fawesome-marketing-machine-learning/lists"}